Embedding Learning Through Multilingual Concept Induction

Dufter, Philipp; Zhao, Mengjie; Schmitt, Martin; Fraser, Alexander und Schütze, Hinrich (Juli 2018): Embedding Learning Through Multilingual Concept Induction. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, July 15-20, 2018. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics Bd. 1 Association for Computational Linguistics. S. 1520-1530

Abstract

We present a new method for estimating vector space representations of words: embedding learning by concept induction. We test this method on a highly parallel corpus and learn semantic representations of words in 1259 different languages in a single common space. An extensive experimental evaluation on crosslingual word similarity and sentiment analysis indicates that concept-based multilingual embedding learning performs better than previous approaches.

• Dokumententyp: Konferenzbeitrag (Paper)
• EU Funded Grant Agreement Number: 740516
• EU-Projekte: Horizon 2020 > ERC Grants > ERC Advanced Grant > ERC Grant 740516: NonSequeToR - Non-sequence models for tokenization replacement
• Fakultätsübergreifende Einrichtungen: Centrum für Informations- und Sprachverarbeitung (CIS)
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 000 Informatik, Wissen, Systeme ; 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik ; 400 Sprache > 400 Sprache ; 400 Sprache > 410 Linguistik
• ISBN: 978-1-948087-32-2
• Sprache: Englisch